CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement

Guirong Chen, Shuqi Ye, Wenkai Yang, Shiqi Shen, Guangyao Shen, Yankai Lin 0001. CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 28632-28653, Association for Computational Linguistics, 2026. [doi]

Authors

Guirong Chen

This author has not been identified. Look up 'Guirong Chen' in Google

Shuqi Ye

This author has not been identified. Look up 'Shuqi Ye' in Google

Wenkai Yang

This author has not been identified. Look up 'Wenkai Yang' in Google

Shiqi Shen

This author has not been identified. Look up 'Shiqi Shen' in Google

Guangyao Shen

This author has not been identified. Look up 'Guangyao Shen' in Google

Yankai Lin 0001

This author has not been identified. Look up 'Yankai Lin 0001' in Google